Cover Image

Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spaces

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Pan, Chaofan, Liu, Jiafen, Li, Yanhua, Xiong, Linbo, Min, Fan, Wei, Wei, Yang, Xin
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Multi-granularity Knowledge Transfer for Continual Reinforcement Learning
by: Pan, Chaofan, et al.
Published: (2024)

Regime-Adaptive Continual Learning for Portfolio Management
by: Pan, Chaofan, et al.
Published: (2026)

A Survey of Continual Reinforcement Learning
by: Pan, Chaofan, et al.
Published: (2025)

Discretizing Continuous Action Space with Unimodal Probability Distributions for On-Policy Reinforcement Learning
by: Zhu, Yuanyang, et al.
Published: (2024)

On the Geometry of Reinforcement Learning in Continuous State and Action Spaces
by: Tiwari, Saket, et al.
Published: (2022)

Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space
by: Liu, Qianmei, et al.
Published: (2024)

Bayesian Off-Policy Evaluation and Learning for Large Action Spaces
by: Aouali, Imad, et al.
Published: (2024)

Provably Efficient Action-Manipulation Attack Against Continuous Reinforcement Learning
by: Luo, Zhi, et al.
Published: (2024)

Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces
by: Tiwari, Saket, et al.
Published: (2025)

Adaptive Advantage-Guided Policy Regularization for Offline Reinforcement Learning
by: Liu, Tenglong, et al.
Published: (2024)

Low-Rank MDPs with Continuous Action Spaces
by: Bennett, Andrew, et al.
Published: (2023)

Policy Optimization in Hybrid Discrete-Continuous Action Spaces via Mixed Gradients
by: Alvo, Matias, et al.
Published: (2026)

CAMEL: Continuous Action Masking Enabled by Large Language Models for Reinforcement Learning
by: Zhao, Yanxiao, et al.
Published: (2025)

Preferred-Action-Optimized Diffusion Policies for Offline Reinforcement Learning
by: Zhang, Tianle, et al.
Published: (2024)

State-Action Inpainting Diffuser for Continuous Control with Delay
by: Han, Dongqi, et al.
Published: (2026)

Off-OAB: Off-Policy Policy Gradient Method with Optimal Action-Dependent Baseline
by: Meng, Wenjia, et al.
Published: (2024)

SAINT: Attention-Based Policies for Discrete Combinatorial Action Spaces
by: Landers, Matthew, et al.
Published: (2025)

Towards General Computer Control with Hierarchical Agents and Multi-Level Action Spaces
by: Dong, Zihan, et al.
Published: (2025)

Learning Action Embeddings for Off-Policy Evaluation
by: Cief, Matej, et al.
Published: (2023)

In-Context Reinforcement Learning for Variable Action Spaces
by: Sinii, Viacheslav, et al.
Published: (2023)

Adaptive Action Duration with Contextual Bandits for Deep Reinforcement Learning in Dynamic Environments
by: Verma, Abhishek, et al.
Published: (2025)

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
by: Fan, Jiajun, et al.
Published: (2025)

Counterfactual Explanations for Continuous Action Reinforcement Learning
by: Dong, Shuyang, et al.
Published: (2025)

Distributions as Actions: A Unified Framework for Diverse Action Spaces
by: He, Jiamin, et al.
Published: (2025)

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
by: Akkerman, Fabian, et al.
Published: (2023)

Learning Agents With Prioritization and Parameter Noise in Continuous State and Action Space
by: Mangannavar, Rajesh, et al.
Published: (2024)

Adaptive Segment-level Reward: Bridging the Gap Between Action and Reward Space in Alignment
by: Li, Yanshi, et al.
Published: (2024)

Model-based Reinforcement Learning for Parameterized Action Spaces
by: Zhang, Renhao, et al.
Published: (2024)

Learning to Generate All Feasible Actions
by: Theile, Mirco, et al.
Published: (2023)

Adaptive Variational Continual Learning via Task-Heuristic Modelling
by: Yang, Fan
Published: (2024)

Incentivizing Safer Actions in Policy Optimization for Constrained Reinforcement Learning
by: Hazra, Somnath, et al.
Published: (2025)

Continual Task Learning through Adaptive Policy Self-Composition
by: Hu, Shengchao, et al.
Published: (2024)

Pretrained Vision-Language-Action Models are Surprisingly Resistant to Forgetting in Continual Learning
by: Liu, Huihan, et al.
Published: (2026)

CRL-VLA: Continual Vision-Language-Action Learning
by: Zeng, Qixin, et al.
Published: (2026)

Learning Native Continuation for Action Chunking Flow Policies
by: Liu, Yufeng, et al.
Published: (2026)

Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
by: Alles, Marvin, et al.
Published: (2024)

Dual Action Policy for Robust Sim-to-Real Reinforcement Learning
by: Terence, Ng Wen Zheng, et al.
Published: (2024)

Transfer Reinforcement Learning in Heterogeneous Action Spaces using Subgoal Mapping
by: Sivakumar, Kavinayan P., et al.
Published: (2024)

An Advantage-based Optimization Method for Reinforcement Learning in Large Action Space
by: Lin, Hai, et al.
Published: (2024)

Mean Flow Policy with Instantaneous Velocity Constraint for One-step Action Generation
by: Zhan, Guojian, et al.
Published: (2026)